Fast binary-based video descriptors for action recognition

Roberto Leyva, Victor Sanchez, Chang Tsun-Li

    Research output: Book chapter/Published conference paperConference paperpeer-review

    6 Citations (Scopus)

    Abstract

    Action recognition is one of the top challenges in computer vision. In this paper, we present two binary-based video descriptors with outstanding characteristics in terms of recognition rate, computational times and memory requirements. The descriptors are called Binary Wavelet Differences (BWD) and Binary Dense Trajectories (BDT). Our proposed descriptors are based on the local binary patterns and produce binary vectors with a very low dimensionality. Specifically, we propose to analyze the spatio-temporal support regions of a video sequence to generate binary strings via wavelets patterns. We also propose to encode the motion information obtained from optical flow into a compact binary representation. Our evaluations on the KTH and UCF50 datasets demonstrate that our proposed descriptors achieve very competitive recognition accuracy. Moreover, they are able to attain shorter computational times and smaller memory requirements. Specifically, our proposed descriptors can be calculated up to 20X faster than orientation-based descriptors and require up to 225X less memory. Due to its binary nature, associated calculations in action recognition, e.g. clustering and classification, can be done up to 40X faster than state-of-the-art descriptors. Finally, our descriptors require codebooks with 2X fewer words than those required by other state-of-the-art descriptors.
    Original languageEnglish
    Title of host publicationProceedings of the 2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
    Place of PublicationUnited States
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-8
    Number of pages8
    ISBN (Electronic)9781509028962
    ISBN (Print)9781509028979
    DOIs
    Publication statusPublished - 2016
    Event2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA) - Mantra on View Hotel, Surfer's Paradise, Gold Coast, Australia
    Duration: 30 Nov 201602 Dec 2016
    http://dicta2016.dictaconference.org/

    Conference

    Conference2016 International Conference on Digital Image Computing: Techniques and Applications (DICTA)
    Country/TerritoryAustralia
    CitySurfer's Paradise, Gold Coast
    Period30/11/1602/12/16
    Internet address

    Fingerprint

    Dive into the research topics of 'Fast binary-based video descriptors for action recognition'. Together they form a unique fingerprint.

    Cite this